{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.9409822821617126, "min": 0.8106604218482971, "max": 1.4315940141677856, "count": 11 }, "Pyramids.Policy.Entropy.sum": { "value": 28199.357421875, "min": 24293.87109375, "max": 43428.8359375, "count": 11 }, "Pyramids.Step.mean": { "value": 329926.0, "min": 29964.0, "max": 329926.0, "count": 11 }, "Pyramids.Step.sum": { "value": 329926.0, "min": 29964.0, "max": 329926.0, "count": 11 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": -0.0634525865316391, "min": -0.10931471735239029, "max": 0.1417982578277588, "count": 11 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": -15.292074203491211, "min": -26.5634765625, "max": 33.74798583984375, "count": 11 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.016926150768995285, "min": 0.009418807923793793, "max": 0.2643304169178009, "count": 11 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 4.079202175140381, "min": 2.2793514728546143, "max": 62.910640716552734, "count": 11 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06600042445598502, "min": 0.06600042445598502, "max": 0.0743068092511399, "count": 11 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9240059423837902, "min": 0.5201476647579794, "max": 1.029499423779449, "count": 11 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.000861378460589898, "min": 0.0006144177248290402, "max": 0.008378806599306973, "count": 11 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.012059298448258572, "min": 0.008601848147606563, "max": 0.058651646195148815, "count": 11 }, "Pyramids.Policy.LearningRate.mean": { "value": 0.0002052285744476286, "min": 0.0002052285744476286, "max": 0.0002952378873016572, "count": 11 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0028732000422668005, "min": 0.0020666652111116, "max": 0.0036344857885047994, "count": 11 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.16840951428571427, "min": 0.16840951428571427, "max": 0.19841262857142855, "count": 11 }, "Pyramids.Policy.Epsilon.sum": { "value": 2.3577331999999998, "min": 1.3888884, "max": 2.6114952000000002, "count": 11 }, "Pyramids.Policy.Beta.mean": { "value": 0.006844110477142855, "min": 0.006844110477142855, "max": 0.009841421594285712, "count": 11 }, "Pyramids.Policy.Beta.sum": { "value": 0.09581754667999998, "min": 0.06888995115999999, "max": 0.12116837048000001, "count": 11 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.020384496077895164, "min": 0.020384496077895164, "max": 0.40739360451698303, "count": 11 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.2853829562664032, "min": 0.2853829562664032, "max": 2.851755142211914, "count": 11 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 987.0, "min": 928.8, "max": 994.7666666666667, "count": 11 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29610.0, "min": 16635.0, "max": 32727.0, "count": 11 }, "Pyramids.Environment.CumulativeReward.mean": { "value": -0.8542933826645215, "min": -0.9320909629265467, "max": -0.5865429045898574, "count": 11 }, "Pyramids.Environment.CumulativeReward.sum": { "value": -25.628801479935646, "min": -30.759001776576042, "max": -14.651000902056694, "count": 11 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": -0.8542933826645215, "min": -0.9320909629265467, "max": -0.5865429045898574, "count": 11 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": -25.628801479935646, "min": -30.759001776576042, "max": -14.651000902056694, "count": 11 }, "Pyramids.Policy.RndReward.mean": { "value": 0.21178404157205175, "min": 0.21178404157205175, "max": 7.58075419418952, "count": 11 }, "Pyramids.Policy.RndReward.sum": { "value": 6.353521247161552, "min": 6.353521247161552, "max": 128.87282130122185, "count": 11 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 11 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 11 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1790770172", "python_version": "3.10.12 (main, Jul 26 2023, 13:20:36) [Clang 16.0.3 ]", "command_line_arguments": "/home/aestoquera/rl_unit5/.venv/bin/mlagents-learn config/ppo/PyramidsRND.yaml --env=training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids1 --no-graphics --torch-device=cpu", "mlagents_version": "1.1.0", "mlagents_envs_version": "1.1.0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.2+cpu", "numpy_version": "1.23.5", "end_time_seconds": "1790770778" }, "total": 605.9252981919999, "count": 1, "self": 0.25963323000178207, "children": { "run_training.setup": { "total": 0.011977090998698259, "count": 1, "self": 0.011977090998698259 }, "TrainerController.start_learning": { "total": 605.6536878709994, "count": 1, "self": 0.46789993205675273, "children": { "TrainerController._reset_env": { "total": 1.238007990999904, "count": 1, "self": 1.238007990999904 }, "TrainerController.advance": { "total": 603.8866585379437, "count": 20863, "self": 0.4164906542864628, "children": { "env_step": { "total": 446.9271373440606, "count": 20863, "self": 416.3892488279962, "children": { "SubprocessEnvManager._take_step": { "total": 30.228820854801597, "count": 20863, "self": 1.244849374088517, "children": { "TorchPolicy.evaluate": { "total": 28.98397148071308, "count": 20735, "self": 28.98397148071308 } } }, "workers": { "total": 0.3090676612628158, "count": 20862, "self": 0.0, "children": { "worker_root": { "total": 604.4669691879244, "count": 20862, "is_parallel": true, "self": 220.13910292412038, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0020890800005872734, "count": 1, "is_parallel": true, "self": 0.0009838019977905788, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011052780027966946, "count": 8, "is_parallel": true, "self": 0.0011052780027966946 } } }, "UnityEnvironment.step": { "total": 0.03427367400217918, "count": 1, "is_parallel": true, "self": 0.00025513300352031365, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0002513659965188708, "count": 1, "is_parallel": true, "self": 0.0002513659965188708 }, "communicator.exchange": { "total": 0.0327860800025519, "count": 1, "is_parallel": true, "self": 0.0327860800025519 }, "steps_from_proto": { "total": 0.0009810949995880947, "count": 1, "is_parallel": true, "self": 0.00023931499526952393, "children": { "_process_rank_one_or_two_observation": { "total": 0.0007417800043185707, "count": 8, "is_parallel": true, "self": 0.0007417800043185707 } } } } } } }, "UnityEnvironment.step": { "total": 384.327866263804, "count": 20861, "is_parallel": true, "self": 5.795743266084173, "children": { "UnityEnvironment._generate_step_input": { "total": 5.116714509214944, "count": 20861, "is_parallel": true, "self": 5.116714509214944 }, "communicator.exchange": { "total": 356.6689165476164, "count": 20861, "is_parallel": true, "self": 356.6689165476164 }, "steps_from_proto": { "total": 16.746491940888518, "count": 20861, "is_parallel": true, "self": 4.3194765375810675, "children": { "_process_rank_one_or_two_observation": { "total": 12.42701540330745, "count": 166888, "is_parallel": true, "self": 12.42701540330745 } } } } } } } } } } }, "trainer_advance": { "total": 156.54303053959666, "count": 20862, "self": 0.816496380866738, "children": { "process_trajectory": { "total": 23.857649031731853, "count": 20862, "self": 23.857649031731853 }, "_update_policy": { "total": 131.86888512699807, "count": 140, "self": 54.68489155684438, "children": { "TorchPPOOptimizer.update": { "total": 77.18399357015369, "count": 7563, "self": 77.18399357015369 } } } } } } }, "trainer_threads": { "total": 8.359966159332544e-07, "count": 1, "self": 8.359966159332544e-07 }, "TrainerController._save_models": { "total": 0.061120574002416106, "count": 1, "self": 0.0009862810002232436, "children": { "RLTrainer._checkpoint": { "total": 0.06013429300219286, "count": 1, "self": 0.06013429300219286 } } } } } } }